EMNLP

Think Right, Not More: Test-Time Scaling for Numerical Claim Verification

Primakov Chungkham, V Venktesh, Vinay Setty, Avishek Anand

机构 * TU Delft（代尔夫特理工大学） ； Stockholm University（斯德哥尔摩大学） ； University of Stavanger（斯塔万内尔大学） 纠错

Comments Accepted to EMNLP 2025, 19 pages

Multilingual Dialogue Generation and Localization with Dialogue Act Scripting

Justin Vasselli, Eunike Andriani Kardinata, Yusuke Sakai, Taro Watanabe

机构 * Nara Institute of Science and Technology（那拉科学与技术研究所） 纠错

Comments 16 pages, 10 tables, 2 figures, Accepted at EMNLP Main 2025

Fuzzy Reasoning Chain (FRC): An Innovative Reasoning Framework from Fuzziness to Clarity

Ping Chen, Xiang Liu, Zhaoxiang Liu, Zezhou Chen, Xingpeng Zhang, Huan Hu, Zipeng Wang, Kai Wang, Shuming Shi, Shiguo Lian

机构 * Data Science & AI Research Institute, China Unicom（中国unicom数据科学与人工智能研究院） ； Unicom Data Intelligence, China Unicom（中国unicom数据智能） ； School of Computer Science and Software Engineering, Southwest Petroleum University（西南石油大学计算机科学与软件工程学院） 纠错

Comments Accepet by EMNLP 2025 Findings (11 pages, 1 figures)

How Accurate Are LLMs at Multi-Question Answering on Conversational Transcripts?

Xiliang Zhu, Shi Zong, David Rossouw

机构 * Dialpad Inc.（Dialpad公司） 纠错

Comments Accepted by EMNLP 2025 Industry Track

MMPlanner: Zero-Shot Multimodal Procedural Planning with Chain-of-Thought Object State Reasoning

Afrina Tabassum, Bin Guo, Xiyao Ma, Hoda Eldardiry, Ismini Lourentzou

机构 * Amazon（亚马逊公司） ； Alexa, Amazon（亚马逊Alexa部门） ； Virginia Tech（弗吉尼亚理工大学） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

Comments 17 pages, 9 figures, 14 tables, Findings of the Association for Computational Linguistics: EMNLP 2025

LLMs for Bayesian Optimization in Scientific Domains: Are We There Yet?

Rushil Gupta, Jason Hartford, Bang Liu

机构 * DIRO, Université de Montréal & Institut Courtois（蒙特利尔大学DIRO与Courtois研究所） ； Mila - Quebec AI Institute（魁北克人工智能研究所） ； The University of Manchester（曼彻斯特大学） ； Valence Labs（Valence实验室） ； Canada CIFAR AI Chair（加拿大CIFAR人工智能主席） 纠错

Comments Accepted to EMNLP 2025

DivLogicEval: A Framework for Benchmarking Logical Reasoning Evaluation in Large Language Models

Tsz Ting Chung, Lemao Liu, Mo Yu, Dit-Yan Yeung

机构 * The Hong Kong University of Science and Technology（香港科技大学） ； Fudan University（复旦大学） ； WeChat AI, Tencent（腾讯微信AI） 纠错

Comments Accepted by EMNLP 2025. Project Page: https://ttchungc.github.io/projects/divlogiceval/

Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling

Yue Zhao, Xiaoyu Wang, Dan Wang, Zhonglin Jiang, Qingqing Gu, Teng Chen, Ningyuan Xi, Jinxian Qu, Yong Chen, Luo Ji

机构 * Geely AI Lab（Geely人工智能实验室） ； Beijing Institute of Technology（北京理工大学） 纠错

Comments Accepted to EMNLP 2025 Findings

Conflict-Aware Soft Prompting for Retrieval-Augmented Generation

Eunseong Choi, June Park, Hyeri Lee, Jongwuk Lee

Comments Accepted to EMNLP 2025; 15 pages; 5 figures, 11 tables; Code available at https://github.com/eunseongc/CARE

Persona-Augmented Benchmarking: Evaluating LLMs Across Diverse Writing Styles

Kimberly Le Truong, Riccardo Fogliato, Hoda Heidari, Zhiwei Steven Wu

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Amazon AWS（亚马逊AWS） 纠错

Comments Accepted to EMNLP 2025

Table-R1: Inference-Time Scaling for Table Reasoning

Zheyuan Yang, Lyuhao Chen, Arman Cohan, Yilun Zhao

机构 * Yale NLP Lab（耶鲁大学自然语言处理实验室） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments EMNLP 2025

SOLAR: Towards Characterizing Subjectivity of Individuals through Modeling Value Conflicts and Trade-offs

Younghun Lee, Dan Goldwasser

机构 * Department of Computer Science（计算机科学系） 纠错

Comments Accepted to the Main Conference at EMNLP 2025. 9 pages

Beyond A Single AI Cluster: A Survey of Decentralized LLM Training

Haotian Dong, Jingyan Jiang, Rongwei Lu, Jiajun Luo, Jiajun Song, Bowen Li, Ying Shen, Zhi Wang

Comments EMNLP 2025

Retrieval-Augmented Generation with Hierarchical Knowledge

Haoyu Huang, Yongfeng Huang, Junjie Yang, Zhenyu Pan, Yongqiang Chen, Kaili Ma, Hongzhi Chen, James Cheng

机构 * CSE, The Chinese University of Hong Kong（计算机科学与工程系，香港中文大学） 纠错

Comments EMNLP 2025 Findings

Cost-Optimal Grouped-Query Attention for Long-Context Modeling

Yingfa Chen, Yutong Wu, Chenyang Song, Zhen Leng Thai, Xingyu Shen, Xu Han, Zhiyuan Liu, Maosong Sun

机构 * NLP Group, DCST, IAI, BNRIST, Tsinghua University, Beijing, China（自然语言处理组、国防科技大学、人工智能院、北京理工大学、清华大学、北京、中国） ； SIST, University of Science and Technology Beijing, Beijing, China（软件学院、北京科技大学、北京、中国） 纠错

Comments EMNLP 2025 Main

Improving LLM-as-a-Judge Inference with the Judgment Distribution

Victor Wang, Michael J. Q. Zhang, Eunsol Choi

机构 * Department of Computer Science（计算机科学系） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） ； New York University（纽约大学） 纠错

Comments EMNLP 2025 Findings

Generator-Assistant Stepwise Rollback Framework for Large Language Model Agent

Xingzuo Li, Kehai Chen, Yunfei Long, Xuefeng Bai, Yong Xu, Min Zhang

机构 * School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China（计算机科学与技术学院，哈尔滨工业大学深圳校区） ； School of Electronic Engineering and Computer Science, Queen Mary University of London（电子工程与计算机科学学院，Queen Mary大学伦敦校区） 纠错

Comments EMNLP 2025 Main

Adaptively profiling models with task elicitation

Davis Brown, Prithvi Balehannina, Helen Jin, Shreya Havaldar, Hamed Hassani, Eric Wong

Comments EMNLP 2025 Main Conference

RuCCoD: Towards Automated ICD Coding in Russian

Aleksandr Nesterov, Andrey Sakhovskiy, Ivan Sviridov, Airat Valiev, Vladimir Makharev, Petr Anokhin, Galina Zubkova, Elena Tutubalina

机构 * AIRI ； Sber AI ； Skoltech ； Sber AI Lab ； HSE University（HSE大学） ； Innopolis University（Innopolis大学） ； ISP RAS Research Center for Trusted AI（ISP RAS可信AI研究中心） 纠错

Comments Accepted to EMNLP 2025 (Main Conference)

Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare

Hiba Ahsan, Arnab Sen Sharma, Silvio Amir, David Bau, Byron C. Wallace

机构 * Northeastern University（东北大学） 纠错

Comments Accepted in EMNLP (Findings)

GeoDANO: Geometric VLM with Domain Agnostic Vision Encoder

Seunghyuk Cho, Zhenyue Qin, Yang Liu, Youngbin Choi, Seungbeom Lee, Dongwoo Kim

机构 * Graduate School of Artificial Intelligence, POSTECH（POSTECH人工智能研究生院） ； Department of Computer Science and Engineering, POSTECH（POSTECH计算机科学与工程系） ； Australian National University（澳大利亚国立大学） 纠错

Comments Accepted to EMNLP-Findings 2025

Can LLMs be Good Graph Judge for Knowledge Graph Construction?

Haoyu Huang, Chong Chen, Zeang Sheng, Yang Li, Wentao Zhang

机构 * Hong Kong University of Science and Technology（香港科技大学） ； Huawei Cloud BU（华为云业务部） ； Peking University（北京大学） 纠错

Comments EMNLP 2025 Main

Retrieval over Classification: Integrating Relation Semantics for Multimodal Relation Extraction

Lei Hei, Tingjing Liao, Yingxin Pei, Yiyang Qi, Jiaqi Wang, Ruiting Li, Feiliang Ren

机构 * School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China（计算机科学与工程学院，东北大学，沈阳110819，中国） 纠错

Comments Accepted by EMNLP 2025 Main Conference

VoiceBBQ: Investigating Effect of Content and Acoustics in Social Bias of Spoken Language Model

Junhyuk Choi, Ro-hoon Oh, Jihwan Seol, Bugeun Kim

Comments Accepted EMNLP 2025 main

CafGa: Customizing Feature Attributions to Explain Language Models

Alan Boyle, Furui Cheng, Vilém Zouhar, Mennatallah El-Assady

Comments 6 Pages (excl. bibliography and appendix), 5 Figures and 2 Tables. Will be presented at EMNLP 2025 (Demo Track)

Distilling Many-Shot In-Context Learning into a Cheat Sheet

Ukyo Honda, Soichiro Murakami, Peinan Zhang

机构 * CyberAgent 纠错

Comments Accepted to EMNLP 2025 (Findings)

Leveraging What's Overfixed: Post-Correction via LLM Grammatical Error Overcorrection

Taehee Park, Heejin Do, Gary Geunbae Lee

机构 * Graduate School of Artificial Intelligence, POSTECH, South Korea（POSTECH人工智能研究生院） ； ETH Zurich, ETH AI Center（苏黎世联邦理工学院人工智能中心） ； Department of Computer Science and Engineering, POSTECH, South Korea（POSTECH计算机科学与工程系） 纠错

Comments EMNLP 2025

Seeing Through Words, Speaking Through Pixels: Deep Representational Alignment Between Vision and Language Models

Zoe Wanying He, Sean Trott, Meenakshi Khosla

机构 * Department of Cognitive Science University of California, San Diego（认知科学系，加州大学圣地亚哥分校） 纠错

Comments Accepted at EMNLP 2025 (camera-ready)

Overcoming Black-box Attack Inefficiency with Hybrid and Dynamic Select Algorithms

Abhinay Shankar Belde, Rohit Ramkumar, Jonathan Rusert

机构 * Department of Computer Science（计算机科学系） ； Purdue University（普渡大学） 纠错

Comments 34 pages, 3 figures, Accepted to Findings of EMNLP 2025

RedHerring Attack: Testing the Reliability of Attack Detection

Jonathan Rusert

机构 * Purdue University, Fort Wayne（普渡大学，弗朗西斯维尔） 纠错

Comments 16 pages, 3 figures, Accepted to EMNLP 2025